Navigate
Advertise here

Gemma 4 26B A4B vs Gemma 4 31B

Gemma 4 31B leads on average score with 5.7 vs 5.5. Gemma 4 26B A4B has the lower benchmark cost at $0.031 vs $0.031. Gemma 4 31B is faster at 7.28s vs 10.55s, with pass rates of 42.0% vs 42.0%.

Last updated at: 2026-10-02

Compared models

Rank
#271
Total Output Tokens
17,306
Response Time (avg)
10.55s
Total Cost
$0.031
Rank
#261
Total Output Tokens
15,499
Response Time (avg)
7.28s
Total Cost
$0.031
Recommended model Gemma 4 31B

It has the strongest score in this comparison (5.7) and the best overall balance of cost and response time across all 2 models.

Detailed comparison

Metric Gemma 4 26B A4B Gemma 4 26B A4B none Release: 2026-04-03 Free Available Gemma 4 31B Gemma 4 31B none Release: 2026-04-02 Free Available
Score 5.5 5.7
Rank #271 #261
Reliability 10.0 10.0
Consistency 9.6 9.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 42.0% 42.0%
Flaky tests 1 1
Total Runs 69 69
Cost per result 0.339 0.520
Total Cost $0.031 $0.031
Input Price $0.090 / 1M $0.090 / 1M
Output Price $0.300 / 1M $0.340 / 1M
Cache Read Price $0.050 / 1M $0.050 / 1M
Cache Write Price N/A N/A
Total Input Tokens 280,126 270,970
Output Tokens 17,306 15,499
Reasoning Tokens 0 0
Response Time (avg) 10.55s 7.28s
Response Time (max) 75.76s 44.73s
Response Time (total) 242.57s 152.84s
Parameters 25.2B total (3.8B active) 30.7B
Availability Open source Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#271 Gemma 4 26B A4B

none
Cost
$0.001
Time
39.5s
Tokens
790 tok

#261 Gemma 4 31B

none
Cost
$0.001
Time
12.8s
Tokens
795 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Gemma 4 26B A4B 3.7 7.2 22.2% 1 4.16s 7,736 476 0
Gemma 4 31B 5.5 10.0 33.3% 0 11.19s 8,381 735 0

Quick Compare

Switch Comparison Pair

Dots 3 Note PreviewmediumFree AvailablevsGemma 4 31BnoneFree AvailableGemma 4 31BnoneFree AvailablevsSpace Bunny AlphalowGemma 4 31BnoneFree AvailablevsGPT-5 NanomediumTrinity Large ThinkinghighvsGemma 4 31BnoneFree AvailableGemma 4 31BnoneFree AvailablevsRing 2.6 1tmediumGemma 4 26B A4BnoneFree AvailablevsNemotron 3 SupermediumFree AvailableNorth Mini CodemediumFree AvailablevsGemma 4 26B A4BnoneFree AvailableGemma 4 26B A4BnoneFree AvailablevsHy4 previewlowGemma 4 31BnoneFree AvailablevsLing 3.0 FlashhighGemma 4 26B A4BnoneFree AvailablevsStep 3.5 FlashmediumGemma 4 31BnoneFree AvailablevsNemotron 3 SupermediumFree AvailableGemma 4 26B A4BnoneFree AvailablevsGranite 4.2 8Blow